Allen Institute for AI


Viewing 1-10 of 391 papers
  • Modular Representation Underlies Systematic Generalization in Neural Natural Language Inference Models

    Atticus Geiger, Kyle Richardson, Christopher PottsBlackbox NLP2020In adversarial (challenge) testing, we pose hard generalization tasks in order to gain insights into the solutions found by our models. What properties must a system have in order to succeed at these hard tasks? In this paper, we argue that an essential factor is the ability to form modular… more
  • A Simple and Effective Model for Answering Multi-span Questions

    Elad Segal, Avia Efrat, Mor Shoham, Amir Globerson, Jonathan BerantEMNLP2020Models for reading comprehension (RC) commonly restrict their output space to the set of all single contiguous spans from the input, in order to alleviate the learning problem and avoid the need for a model that generates text explicitly. However, forcing an answer to be a single span can be… more
  • A Simple Yet Strong Pipeline for HotpotQA

    Dirk Groeneveld, Tushar Khot, Mausam, Ashish SabharwalEMNLP2020State-of-the-art models for multi-hop question answering typically augment large-scale language models like BERT with additional, intuitively useful capabilities such as named entity recognition, graph-based reasoning, and question decomposition. However, does their strong performance on popular… more
  • Fact or Fiction: Verifying Scientific Claims

    David Wadden, Kyle Lo, Lucy Lu Wang, Shanchuan Lin, Madeleine van Zuylen, Arman Cohan, Hannaneh HajishirziEMNLP2020We introduce the task of scientific fact-checking. Given a corpus of scientific articles and a claim about a scientific finding, a fact-checking model must identify abstracts that support or refute the claim. In addition, it must provide rationales for its predictions in the form of evidentiary… more
  • Is Multihop QA in DiRe Condition? Measuring and Reducing Disconnected Reasoning

    H. Trivedi, N. Balasubramanian, Tushar Khot, A. SabharwalEMNLP2020Has there been real progress in multi-hop question-answering? Models often exploit dataset artifacts to produce correct answers, without connecting information across multiple supporting facts. This limits our ability to measure true progress and defeats the purpose of building multihop QA datasets… more
  • Learning to Explain: Datasets and Models for Identifying Valid Reasoning Chains in Multihop Question-Answering.

    Harsh Jhamtani, P. ClarkEMNLP2020Despite the rapid progress in multihop question-answering (QA), models still have trouble explaining why an answer is correct, with limited explanation training data available to learn from. To address this, we introduce three explanation datasets in which explanations formed from corpus facts are… more
  • More Bang for Your Buck: Natural Perturbation for Robust Question Answering

    Tao Li, Daniel Khashabi, Tushar Khot, Ashish Sabharwal, V. SrikumarEMNLP2020Warning: This paper contains examples of stereotypes that are potentially offensive. While language embeddings have been shown to have stereotyping biases, how these biases affect downstream question answering (QA) models remains unexplored. We present UNQOVER, a general framework to probe and… more
  • QADiscourse - Discourse Relations as QA Pairs: Representation, Crowdsourcing and Baselines

    Valentina Pyatkin, Ayal Klein, Reut Tsarfaty, Ido DaganEMNLP2020Discourse relations describe how two propositions relate to one another, and identifying them automatically is an integral part of natural language understanding. However, annotating discourse relations typically requires expert annotators. Recently, different semantic aspects of a sentence have… more
  • SciSight: Combining faceted navigation and research group detection for COVID-19 exploratory scientific search

    Tom Hope, Jason Portenoy, Kishore Vasan, Jonathan Borchardt, Eric Horvitz, Daniel S. Weld, Marti A. Hearst, Jevin D. WestEMNLP • Demo2020The COVID-19 pandemic has sparked unprecedented mobilization of scientists, already generating thousands of new papers that join a litany of previous biomedical work in related areas. This deluge of information makes it hard for researchers to keep track of their own field, let alone explore new… more
  • SLEDGE: A Simple Yet Effective Baseline for COVID-19 Scientific Knowledge Search

    S. MacAvaney, Arman Cohan, N. GoharianEMNLP2020With worldwide concerns surrounding the Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2), there is a rapidly growing body of literature on the virus. Clinicians, researchers, and policy-makers need a way to effectively search these articles. In this work, we present a search system… more